62 citations · 62 across the 12 of their papers we have counts for
7 papers · 1 filter
Explaining the Saliency Map Sparsity of Adversarially-Trained Neural Networks
Yannick Lunk, Atell Yehor Krasnopolsky, Damien Garreau +1
Understanding why deep neural networks make a given prediction is of great importance for their safe deployment. In computer vision, saliency maps, which highlight the image region…
Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbations
Josef Lindl, Mariana Chaves, Damien Garreau
The increasing complexity of state-of-the-art machine learning models has made their behavior progressively harder to interpret, spurring rapid advancements in the field of eXplain…
Towards Understanding Steering Strength
Magamed Taimeskhanov, Samuel Vaiter, Damien Garreau
A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction dependi…
When Are Two Scores Better Than One? Investigating Ensembles of Diffusion Models
Raphaël Razafindralambo, Rémy Sun, Frédéric Precioso +2
Diffusion models now generate high-quality, diverse samples, with an increasing focus on more powerful models. Although ensembling is a well-known way to improve supervised models,…
On The Variability of Concept Activation Vectors
Julia Wenkmann, Damien Garreau
One of the most pressing challenges in artificial intelligence is to make models more transparent to their users. Recently, explainable artificial intelligence has come up with num…
Feature Attribution from First Principles
Magamed Taimeskhanov, Damien Garreau
Feature attribution methods are a popular approach to explain the behavior of machine learning models. They assign importance scores to each input feature, quantifying their influe…
GLEAMS: Bridging the Gap Between Local and Global Explanations
Giorgio Visani, Vincenzo Stanzione, Damien Garreau
The explainability of machine learning algorithms is crucial, and numerous methods have emerged recently. Local, post-hoc methods assign an attribution score to each feature, indic…